29 citations · 56 across the 4 of their papers we have counts for
4 papers
Conditional Generative Models for Counterfactual Explanations
Arnaud Van Looveren, Janis Klaise, Giovanni Vacanti +1
Counterfactual instances offer human-interpretable insight into the local behaviour of machine learning models. We propose a general framework to generate sparse, in-distribution c…
Monitoring and explainability of models in production
Janis Klaise, Arnaud Van Looveren, Clive Cox +2
The machine learning lifecycle extends beyond the deployment stage. Monitoring deployed models is crucial for continued provision of high quality machine learning enabled services.…
Adversarial Detection and Correction by Matching Prediction Distributions
Giovanni Vacanti, Arnaud Van Looveren
We present a novel adversarial detection and correction method for machine learning classifiers.The detector consists of an autoencoder trained with a custom loss function based on…
The work cost of keeping states with coherences out of thermal equilibrium
Giovanni Vacanti, Cyril Elouard, Alexia Auffeves
We consider the problem of keeping an arbitrary state out of thermal equilibrium. We find that counter-acting thermalisation using only a resource system which is in a statio…